© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 1946
    Prev
    Next
    INDEX
    Explanations

    describing complexity

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_7_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Ге
    3.41
     製
    3.23
     フラワー
    3.18
     Д
    3.18
     プ
    3.12
     Бо
    3.08
     ブルー
    3.07
     ใส่
    3.02
     県
    3.00
     為
    2.98
    POSITIVE LOGITS
    স্ক
    2.01
    প
    2.00
    O
    1.89
    g
    1.89
    下
    1.87
    回
    1.84
    frame
    1.81
    ச்சு
    1.80
    过
    1.80
    Normal
    1.77
    Activations Density 0.012%

    No Known Activations